WO2023101304A1 - Procédé et appareil de réalisation d'une communication dans un système de communication sans fil - Google Patents

Procédé et appareil de réalisation d'une communication dans un système de communication sans fil Download PDF

Info

Publication number
WO2023101304A1
WO2023101304A1 PCT/KR2022/018624 KR2022018624W WO2023101304A1 WO 2023101304 A1 WO2023101304 A1 WO 2023101304A1 KR 2022018624 W KR2022018624 W KR 2022018624W WO 2023101304 A1 WO2023101304 A1 WO 2023101304A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
mpf
information
base station
terminal
Prior art date
Application number
PCT/KR2022/018624
Other languages
English (en)
Korean (ko)
Inventor
이은종
이경호
김봉회
이상림
Original Assignee
엘지전자 주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 엘지전자 주식회사 filed Critical 엘지전자 주식회사
Priority to KR1020247010151A priority Critical patent/KR20240116893A/ko
Publication of WO2023101304A1 publication Critical patent/WO2023101304A1/fr

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H04B17/318—Received signal strength
    • H04B17/328—Reference signal received power [RSRP]; Reference signal received quality [RSRQ]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/373—Predicting channel quality or other radio frequency [RF] parameters
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
    • H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
    • H04B7/0619—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
    • H04B7/0621—Feedback content
    • H04B7/0626—Channel coefficients, e.g. channel state information [CSI]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B7/00—Radio transmission systems, i.e. using radiation field
    • H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
    • H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
    • H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
    • H04B7/0686—Hybrid systems, i.e. switching and simultaneous transmission
    • H04B7/0695—Hybrid systems, i.e. switching and simultaneous transmission using beam selection
    • H04B7/06952—Selecting one or more beams from a plurality of beams, e.g. beam training, management or sweeping
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/12—Wireless traffic scheduling
    • H04W72/1263—Mapping of traffic onto schedule, e.g. scheduled allocation or multiplexing of flows
    • H04W72/1268—Mapping of traffic onto schedule, e.g. scheduled allocation or multiplexing of flows of uplink data flows
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W72/00—Local resource management
    • H04W72/20—Control channels or signalling for resource management
    • H04W72/21—Control channels or signalling for resource management in the uplink direction of a wireless link, i.e. towards the network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W74/00—Wireless channel access
    • H04W74/08—Non-scheduled access, e.g. ALOHA
    • H04W74/0833—Random access procedures, e.g. with 4-step access

Definitions

  • the following description relates to a wireless communication system, and relates to a method and apparatus for performing communication in the wireless communication system.
  • it relates to a method and apparatus for a terminal to report model performance feedback (MPF) to a base station based on an artificial intelligence (AI)/machine learning (ML) model.
  • MPF model performance feedback
  • AI artificial intelligence
  • ML machine learning
  • a wireless access system is widely deployed to provide various types of communication services such as voice and data.
  • a wireless access system is a multiple access system capable of supporting communication with multiple users by sharing available system resources (bandwidth, transmission power, etc.).
  • Examples of the multiple access system include a code division multiple access (CDMA) system, a frequency division multiple access (FDMA) system, a time division multiple access (TDMA) system, an orthogonal frequency division multiple access (OFDMA) system, and a single carrier frequency (SC-FDMA) system. division multiple access) system.
  • CDMA code division multiple access
  • FDMA frequency division multiple access
  • TDMA time division multiple access
  • OFDMA orthogonal frequency division multiple access
  • SC-FDMA single carrier frequency division multiple access
  • eMBB enhanced mobile broadband
  • RAT radio access technology
  • MTC massive Machine Type Communications
  • the present disclosure relates to a method and apparatus for performing communication in a wireless communication system.
  • the present disclosure relates to a method and apparatus for sharing an AI/ML model in a wireless communication system.
  • the present disclosure relates to a method and apparatus for reporting an MPF for an AI/ML model to a base station in a wireless communication system.
  • the present disclosure relates to a method and apparatus for obtaining MPF setting-related information for MPF reporting on an AI/ML model in a wireless communication system.
  • the present disclosure relates to a method and apparatus for determining information included in an MPF based on an AI/ML model in a wireless communication system.
  • the terminal receives a synchronization signal from a base station, transmits a random access preamble to the base station based on the synchronization signal, and generates a random access preamble based on the random access preamble.
  • Receiving an access response performing connection with a base station after receiving a random access response, artificial intelligence (AI) / machine learning (ML) model information from the base station, and model performance feedback for the AI / ML model MPF) receiving at least one of related information, performing model inference in the AI/ML model based on the AI/ML model information, and transmitting the MPF of the AI/ML model to the base station through model performance evaluation. It may include the step of determining whether or not.
  • a method of operating a base station in a wireless communication system transmitting a synchronization signal to a terminal, receiving a random access preamble from the terminal based on the synchronization signal, based on the random access preamble to the terminal and transmitting a random access response, and performing a connection with the terminal after receiving the random access response, AI (artificial intelligence) / ML (machine learning) model information and model performance feedback for the AI / ML model performance feedback (MPF), including transmitting at least one of related information, wherein the terminal performs model inference in the AI/ML model based on the AI/ML model information, and evaluates AI/ML performance through model performance evaluation. It is possible to determine whether or not to transmit the MPF of the model to the base station.
  • AI artificial intelligence
  • ML machine learning
  • a terminal of a wireless communication system including a transceiver and a processor connected to the transceiver
  • the processor controls the transceiver so that the terminal receives a synchronization signal from the base station, and based on the synchronization signal Controls the transceiver to transmit a random access preamble to the base station, controls the transceiver to receive a random access response based on the random access preamble, performs connection with the base station after receiving the random access response, and performs artificial intelligence (AI)/receiver from the base station
  • a transceiver is controlled to receive at least one of ML (machine learning) model information and model performance feedback (MPF) related information for the AI/ML model, and the AI/ML model is based on the AI/ML model information. It is possible to perform model inference and determine whether to transmit the MPF of the AI / ML model to the base station through model performance evaluation.
  • ML machine learning
  • MPF model performance feedback
  • a base station of a wireless communication system including a transceiver and a processor connected to the transceiver
  • the processor controls the transceiver to transmit a synchronization signal to a terminal, and from the terminal based on the synchronization signal Controls the transceiver to receive the random access preamble, controls the transceiver to transmit a random access response to the terminal based on the random access preamble, performs connection with the terminal after receiving the random access response, and artificial intelligence (AI) to the terminal / Controls the transceiver to transmit at least one of machine learning (ML) model information and model performance feedback (MPF) related information for the AI / ML model, but the terminal transmits AI based on the AI / ML model information It is possible to perform model inference in the /ML model and determine whether to transmit the MPF of the AI / ML model to the base station through model performance evaluation.
  • ML machine learning
  • MPF model performance feedback
  • the at least one processor receives a synchronization signal from a base station. control the device to transmit a random access preamble to the base station based on the synchronization signal, control the device to receive a random access response based on the random access preamble, and establish a connection with the base station after receiving the random access response Control the device to perform, and to receive at least one of AI (artificial intelligence) / ML (machine learning) model information and model performance feedback (MPF) related information for the AI / ML model from the base station. control, perform model inference in the AI / ML model based on the AI / ML model information, and control the device to determine whether to transmit the MPF of the AI / ML model to the base station through model performance evaluation .
  • AI artificial intelligence
  • ML machine learning
  • MPF model performance feedback
  • At least one executable by a processor includes instructions of, wherein the at least one command controls to receive a synchronization signal from the base station, controls to transmit a random access preamble to the base station based on the synchronization signal, and receives a random access response based on the random access preamble.
  • control control to perform connection with the base station after receiving a random access response, and related to AI (artificial intelligence) / ML (machine learning) model information and model performance feedback (MPF) for the AI / ML model from the base station
  • AI artificial intelligence
  • ML machine learning
  • MPF model performance feedback
  • the MPF related information may include at least one of MPF parameter information of an AI/ML model, MPF triggering condition information, and MPF related data information.
  • the MPF parameters may be identically set in at least one AI/ML model.
  • the MPF parameter information may include at least one of prediction accuracy information of an AI/ML model, channel state information (CSI) feedback information, and information about measurement values.
  • CSI channel state information
  • the terminal when beam prediction is performed based on the AI / ML model, the terminal obtains beam quality prediction accuracy information included in MPF parameter information, but the beam quality prediction accuracy information is obtained by transmitting the MPF to the base station. It includes a preset beam quality prediction accuracy value for determining whether to transmit, and the terminal performs RSRP prediction on at least one beam through model inference based on the AI / ML model to select a beam with the highest RSRP.
  • the MPF triggering condition information includes at least one of threshold value information and transmission method information, but the threshold information includes a threshold value for a feedback value and a threshold value related to update decision of the AI/ML model. includes at least one of, and the transmission method information indicates the MPF transmission method of the AI / ML model, but the MPF is based on at least one of periodic transmission, event-based aperiodic transmission, and model inference execution time transmission can be transmitted
  • the terminal performs an action based on an output of model inference of AI / ML model information, performs model performance evaluation based on the output and the action, and based on the model performance evaluation If it is decided not to transmit the MPF of the AI/ML model, the terminal generates an output based on the model inference of the AI/ML model to perform an action, and transmits the MPF of the AI/ML model based on the model performance evaluation. If it is decided to do so, the terminal may receive updated AI / ML model information from the base station, generate an output based on the updated AI / ML model, and perform an action.
  • whether or not to transmit the MPF of the AI/ML model may be determined based on at least one of an event set by a base station, an event set by a terminal, and a preset event.
  • the MPF when transmission to the MPF is determined, the MPF includes 1-bit indication information indicating a performance state for each AI/ML model, a model performance evaluation result value of the AI/ML model, and model performance evaluation It may include at least one of related data values.
  • the MPF when the MPF includes 1-bit indication information indicating a performance state for each AI/ML model, based on model performance evaluation result value and threshold value comparison based on model inference Accordingly, 1-bit indication information indicating a performance state for each AI/ML model may be determined and included in the MPF.
  • the MPF when the MPF includes the model performance evaluation result value of each AI/ML model, the MPF is a value for the difference between the model performance evaluation result value or the model performance evaluation result value and a preset value. may include any one of them.
  • the MPF when it is determined that the MPF of the AI / ML model is transmitted to the base station, the MPF may be indicated through at least one of a physical uplink control channel (PUCCH) and a physical uplink shared channel (PUSCH). there is.
  • a physical uplink control channel PUCCH
  • PUSCH physical uplink shared channel
  • the MPF when it is determined that the MPF of the AI/ML model is transmitted to the base station, the MPF may be included in a medium access control (MAC) control element (CE) and transmitted.
  • MAC medium access control
  • CE control element
  • the MPF when it is determined that the MPF of the AI / ML model is transmitted to the base station, the MPF is transmitted through an uplink-dedicated control channel based on a radio resource control (RRC) message.
  • RRC radio resource control
  • a method for performing communication may be provided.
  • a method for sharing an AI/ML model may be provided.
  • a method for reporting an MPF for an AI/ML model to a base station may be provided.
  • Embodiments based on the present disclosure may provide a method for obtaining MPF setting related information for MPF reporting on AI/ML models.
  • a method for determining information included in an MPF based on an AI/ML model may be provided.
  • FIG. 1 is a diagram illustrating an exemplary communication system according to an embodiment of the present disclosure.
  • FIG. 2 is a diagram showing an example of a wireless device according to an embodiment of the present disclosure.
  • FIG. 3 is a diagram illustrating another example of a wireless device according to an embodiment of the present disclosure.
  • AI Artificial Intelligence
  • FIG. 5 is a diagram illustrating a functional framework according to an embodiment of the present disclosure.
  • FIG. 6 is a diagram illustrating a method of generating an AI/ML-based model inference output according to an embodiment of the present disclosure.
  • FIG. 7 is a diagram illustrating a method of generating an AI/ML-based model inference output according to an embodiment of the present disclosure.
  • FIG. 8 is a diagram illustrating a case in which both model training and model inference exist in the RAN according to an embodiment of the present disclosure.
  • FIG. 9 is a diagram illustrating a method in which AI/ML-based model training is performed in a network and model inference is performed in a terminal according to an embodiment of the present disclosure.
  • FIG. 10 is a diagram illustrating a method in which AI/ML-based model training is performed in a network and model inference is performed in a network and a terminal according to an embodiment of the present disclosure.
  • FIG. 11 is a diagram illustrating a method of performing MPF transmission applicable to the present disclosure.
  • the 12 may be a MAC CE format in which information included in an MPF applicable to the present disclosure is transmitted.
  • FIG. 13 is a diagram illustrating a terminal operation applicable to the present disclosure.
  • FIG. 14 is a diagram illustrating UE operation based on beam prediction applicable to the present disclosure.
  • 15 is a flowchart illustrating a terminal operation applicable to the present disclosure.
  • 16 is a flowchart illustrating a terminal operation applicable to the present disclosure.
  • each component or feature may be considered optional unless explicitly stated otherwise.
  • Each component or feature may be implemented in a form not combined with other components or features.
  • an embodiment of the present disclosure may be configured by combining some elements and/or features. The order of operations described in the embodiments of the present disclosure may be changed. Some components or features of one embodiment may be included in another embodiment, or may be replaced with corresponding components or features of another embodiment.
  • a base station has meaning as a terminal node of a network that directly communicates with a mobile station.
  • a specific operation described as being performed by a base station in this document may be performed by an upper node of the base station in some cases.
  • the 'base station' is a term such as a fixed station, Node B, eNode B, gNode B, ng-eNB, advanced base station (ABS), or access point. can be replaced by
  • a terminal includes a user equipment (UE), a mobile station (MS), a subscriber station (SS), a mobile subscriber station (MSS), It may be replaced with terms such as mobile terminal or advanced mobile station (AMS).
  • UE user equipment
  • MS mobile station
  • SS subscriber station
  • MSS mobile subscriber station
  • AMS advanced mobile station
  • the transmitting end refers to a fixed and/or mobile node providing data service or voice service
  • the receiving end refers to a fixed and/or mobile node receiving data service or voice service. Therefore, in the case of uplink, the mobile station can be a transmitter and the base station can be a receiver. Similarly, in the case of downlink, the mobile station may be a receiving end and the base station may be a transmitting end.
  • Embodiments of the present disclosure are wireless access systems, such as an IEEE 802.xx system, a 3rd Generation Partnership Project (3GPP) system, a 3GPP Long Term Evolution (LTE) system, a 3GPP 5G (5th generation) NR (New Radio) system, and a 3GPP2 system. It may be supported by at least one disclosed standard document, and in particular, the embodiments of the present disclosure are supported by 3GPP technical specification (TS) 38.211, 3GPP TS 38.212, 3GPP TS 38.213, 3GPP TS 38.321 and 3GPP TS 38.331 documents It can be.
  • 3GPP technical specification TS 38.211, 3GPP TS 38.212, 3GPP TS 38.213, 3GPP TS 38.321 and 3GPP TS 38.331 documents It can be.
  • embodiments of the present disclosure may be applied to other wireless access systems, and are not limited to the above-described systems.
  • it may also be applicable to a system applied after the 3GPP 5G NR system, and is not limited to a specific system.
  • CDMA code division multiple access
  • FDMA frequency division multiple access
  • TDMA time division multiple access
  • OFDMA orthogonal frequency division multiple access
  • SC-FDMA single carrier frequency division multiple access
  • LTE is 3GPP TS 36.xxx Release 8 or later
  • LTE technology after 3GPP TS 36.xxx Release 10 is referred to as LTE-A
  • xxx Release 13 may be referred to as LTE-A pro.
  • 3GPP NR may mean technology after TS 38.xxx Release 15.
  • 3GPP 6G may mean technology after TS Release 17 and/or Release 18.
  • "xxx" means a standard document detail number.
  • LTE/NR/6G may be collectively referred to as a 3GPP system.
  • FIG. 1 is a diagram illustrating an example of a communication system applied to the present disclosure.
  • a communication system 100 applied to the present disclosure includes a wireless device, a base station, and a network.
  • the wireless device means a device that performs communication using a radio access technology (eg, 5G NR, LTE), and may be referred to as a communication/wireless/5G device.
  • the wireless device includes a robot 100a, a vehicle 100b-1 and 100b-2, an extended reality (XR) device 100c, a hand-held device 100d, and a home appliance. appliance) 100e, Internet of Thing (IoT) device 100f, and artificial intelligence (AI) device/server 100g.
  • a radio access technology eg, 5G NR, LTE
  • XR extended reality
  • IoT Internet of Thing
  • AI artificial intelligence
  • the vehicle may include a vehicle equipped with a wireless communication function, an autonomous vehicle, a vehicle capable of performing inter-vehicle communication, and the like.
  • the vehicles 100b-1 and 100b-2 may include an unmanned aerial vehicle (UAV) (eg, a drone).
  • UAV unmanned aerial vehicle
  • the XR device 100c includes augmented reality (AR)/virtual reality (VR)/mixed reality (MR) devices, and includes a head-mounted device (HMD), a head-up display (HUD) installed in a vehicle, a television, It may be implemented in the form of smart phones, computers, wearable devices, home appliances, digital signage, vehicles, robots, and the like.
  • the mobile device 100d may include a smart phone, a smart pad, a wearable device (eg, a smart watch, a smart glass), a computer (eg, a laptop computer), and the like.
  • the home appliance 100e may include a TV, a refrigerator, a washing machine, and the like.
  • the IoT device 100f may include a sensor, a smart meter, and the like.
  • the base station 120 and the network 130 may also be implemented as a wireless device, and a specific wireless device 120a may operate as a base station/network node to other wireless devices.
  • the wireless devices 100a to 100f may be connected to the network 130 through the base station 120 .
  • AI technology may be applied to the wireless devices 100a to 100f, and the wireless devices 100a to 100f may be connected to the AI server 100g through the network 130.
  • the network 130 may be configured using a 3G network, a 4G (eg LTE) network, or a 5G (eg NR) network.
  • the wireless devices 100a to 100f may communicate with each other through the base station 120/network 130, but communicate directly without going through the base station 120/network 130 (e.g., sidelink communication). You may.
  • the vehicles 100b-1 and 100b-2 may perform direct communication (eg, vehicle to vehicle (V2V)/vehicle to everything (V2X) communication).
  • the IoT device 100f eg, sensor
  • the IoT device 100f may directly communicate with other IoT devices (eg, sensor) or other wireless devices 100a to 100f.
  • FIG. 2 is a diagram illustrating an example of a wireless device applicable to the present disclosure.
  • a first wireless device 200a and a second wireless device 200b may transmit and receive radio signals through various wireless access technologies (eg, LTE and NR).
  • ⁇ the first wireless device 200a, the second wireless device 200b ⁇ denotes the ⁇ wireless device 100x and the base station 120 ⁇ of FIG. 1 and/or the ⁇ wireless device 100x and the wireless device 100x.
  • ⁇ can correspond.
  • the first wireless device 200a includes one or more processors 202a and one or more memories 204a, and may further include one or more transceivers 206a and/or one or more antennas 208a.
  • the processor 202a controls the memory 204a and/or the transceiver 206a and may be configured to implement the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein.
  • the processor 202a may process information in the memory 204a to generate first information/signal, and transmit a radio signal including the first information/signal through the transceiver 206a.
  • the processor 202a may receive a radio signal including the second information/signal through the transceiver 206a and store information obtained from signal processing of the second information/signal in the memory 204a.
  • the memory 204a may be connected to the processor 202a and may store various information related to the operation of the processor 202a.
  • memory 204a may perform some or all of the processes controlled by processor 202a, or instructions for performing the descriptions, functions, procedures, suggestions, methods, and/or flowcharts of operations disclosed herein. It may store software codes including them.
  • the processor 202a and the memory 204a may be part of a communication modem/circuit/chip designed to implement a wireless communication technology (eg, LTE, NR).
  • the transceiver 206a may be coupled to the processor 202a and may transmit and/or receive wireless signals through one or more antennas 208a.
  • the transceiver 206a may include a transmitter and/or a receiver.
  • the transceiver 206a may be used interchangeably with a radio frequency (RF) unit.
  • RF radio frequency
  • a wireless device may mean a communication modem/circuit/chip.
  • the second wireless device 200b includes one or more processors 202b, one or more memories 204b, and may further include one or more transceivers 206b and/or one or more antennas 208b.
  • the processor 202b controls the memory 204b and/or the transceiver 206b and may be configured to implement the descriptions, functions, procedures, suggestions, methods and/or operational flow diagrams disclosed herein.
  • the processor 202b may process information in the memory 204b to generate third information/signal, and transmit a radio signal including the third information/signal through the transceiver 206b.
  • the processor 202b may receive a radio signal including the fourth information/signal through the transceiver 206b and store information obtained from signal processing of the fourth information/signal in the memory 204b.
  • the memory 204b may be connected to the processor 202b and may store various information related to the operation of the processor 202b.
  • the memory 204b may perform some or all of the processes controlled by the processor 202b, or instructions for performing the descriptions, functions, procedures, suggestions, methods, and/or flowcharts of operations disclosed herein. It may store software codes including them.
  • the processor 202b and the memory 204b may be part of a communication modem/circuit/chip designed to implement a wireless communication technology (eg, LTE, NR).
  • the transceiver 206b may be coupled to the processor 202b and may transmit and/or receive wireless signals through one or more antennas 208b.
  • the transceiver 206b may include a transmitter and/or a receiver.
  • the transceiver 206b may be used interchangeably with an RF unit.
  • a wireless device may mean a communication modem/circuit/chip.
  • one or more protocol layers may be implemented by one or more processors 202a, 202b.
  • the one or more processors 202a and 202b may include one or more layers (eg, PHY (physical), MAC (media access control), RLC (radio link control), PDCP (packet data convergence protocol), RRC (radio resource) control) and functional layers such as service data adaptation protocol (SDAP).
  • One or more processors 202a, 202b may generate one or more protocol data units (PDUs) and/or one or more service data units (SDUs) according to the descriptions, functions, procedures, proposals, methods, and/or operational flow charts disclosed herein.
  • PDUs protocol data units
  • SDUs service data units
  • processors 202a, 202b may generate messages, control information, data or information according to the descriptions, functions, procedures, proposals, methods and/or operational flow diagrams disclosed herein.
  • One or more processors 202a, 202b generate PDUs, SDUs, messages, control information, data or signals (eg, baseband signals) containing information according to the functions, procedures, proposals and/or methods disclosed herein , may be provided to one or more transceivers 206a and 206b.
  • One or more processors 202a, 202b may receive signals (eg, baseband signals) from one or more transceivers 206a, 206b, and descriptions, functions, procedures, suggestions, methods, and/or flowcharts of operations disclosed herein PDUs, SDUs, messages, control information, data or information can be obtained according to these.
  • signals eg, baseband signals
  • One or more processors 202a, 202b may be referred to as a controller, microcontroller, microprocessor or microcomputer.
  • One or more processors 202a, 202b may be implemented by hardware, firmware, software, or a combination thereof.
  • ASICs application specific integrated circuits
  • DSPs digital signal processors
  • DSPDs digital signal processing devices
  • PLDs programmable logic devices
  • FPGAs field programmable gate arrays
  • firmware or software may be implemented using firmware or software, and the firmware or software may be implemented to include modules, procedures, functions, and the like.
  • Firmware or software configured to perform the descriptions, functions, procedures, proposals, methods and/or operational flow charts disclosed in this document may be included in one or more processors 202a or 202b or stored in one or more memories 204a or 204b. It can be driven by the above processors 202a and 202b.
  • the descriptions, functions, procedures, suggestions, methods and/or operational flow charts disclosed in this document may be implemented using firmware or software in the form of codes, instructions and/or sets of instructions.
  • One or more memories 204a, 204b may be coupled to one or more processors 202a, 202b and may store various types of data, signals, messages, information, programs, codes, instructions and/or instructions.
  • One or more memories 204a, 204b may include read only memory (ROM), random access memory (RAM), erasable programmable read only memory (EPROM), flash memory, hard drive, registers, cache memory, computer readable storage media, and/or It may consist of a combination of these.
  • One or more memories 204a, 204b may be located internally and/or externally to one or more processors 202a, 202b.
  • one or more memories 204a, 204b may be connected to one or more processors 202a, 202b through various technologies such as wired or wireless connections.
  • One or more transceivers 206a, 206b may transmit user data, control information, radio signals/channels, etc. referred to in the methods and/or operational flow charts of this document to one or more other devices.
  • One or more transceivers 206a, 206b may receive user data, control information, radio signals/channels, etc. referred to in descriptions, functions, procedures, proposals, methods and/or operational flow charts, etc. disclosed herein from one or more other devices. there is.
  • one or more transceivers 206a and 206b may be connected to one or more processors 202a and 202b and transmit and receive radio signals.
  • one or more processors 202a, 202b may control one or more transceivers 206a, 206b to transmit user data, control information, or radio signals to one or more other devices.
  • one or more processors 202a, 202b may control one or more transceivers 206a, 206b to receive user data, control information, or radio signals from one or more other devices.
  • one or more transceivers 206a, 206b may be coupled to one or more antennas 208a, 208b, and one or more transceivers 206a, 206b may be connected to one or more antennas 208a, 208b to achieve the descriptions, functions disclosed in this document.
  • one or more antennas may be a plurality of physical antennas or a plurality of logical antennas (eg, antenna ports).
  • One or more transceivers (206a, 206b) in order to process the received user data, control information, radio signal / channel, etc. using one or more processors (202a, 202b), the received radio signal / channel, etc. in the RF band signal It can be converted into a baseband signal.
  • One or more transceivers 206a and 206b may convert user data, control information, and radio signals/channels processed by one or more processors 202a and 202b from baseband signals to RF band signals.
  • one or more transceivers 206a, 206b may include (analog) oscillators and/or filters.
  • FIG. 3 is a diagram illustrating another example of a wireless device applied to the present disclosure.
  • a wireless device 300 corresponds to the wireless devices 200a and 200b of FIG. 2, and includes various elements, components, units/units, and/or modules. ) can be configured.
  • the wireless device 300 may include a communication unit 310, a control unit 320, a memory unit 330, and an additional element 340.
  • the communication unit may include communication circuitry 312 and transceiver(s) 314 .
  • communication circuitry 312 may include one or more processors 202a, 202b of FIG. 2 and/or one or more memories 204a, 204b.
  • transceiver(s) 314 may include one or more transceivers 206a, 206b of FIG.
  • the control unit 320 is electrically connected to the communication unit 310, the memory unit 330, and the additional element 340 and controls overall operations of the wireless device. For example, the control unit 320 may control electrical/mechanical operations of the wireless device based on programs/codes/commands/information stored in the memory unit 330. In addition, the control unit 320 transmits the information stored in the memory unit 330 to the outside (eg, another communication device) through the communication unit 310 through a wireless/wired interface, or transmits the information stored in the memory unit 330 to the outside (eg, another communication device) through the communication unit 310. Information received through a wireless/wired interface from other communication devices) may be stored in the memory unit 330 .
  • the additional element 340 may be configured in various ways according to the type of wireless device.
  • the additional element 340 may include at least one of a power unit/battery, an input/output unit, a driving unit, and a computing unit.
  • the wireless device 300 may be a robot (FIG. 1, 100a), a vehicle (FIG. 1, 100b-1, 100b-2), an XR device (FIG. 1, 100c), a mobile device (FIG. 1, 100d) ), home appliances (FIG. 1, 100e), IoT devices (FIG.
  • Wireless devices can be mobile or used in a fixed location depending on the use-case/service.
  • various elements, components, units/units, and/or modules in the wireless device 300 may be entirely interconnected through a wired interface or at least partially connected wirelessly through the communication unit 310 .
  • the control unit 320 and the communication unit 310 are connected by wire, and the control unit 320 and the first units (eg, 130 and 140) are connected wirelessly through the communication unit 310.
  • each element, component, unit/unit, and/or module within wireless device 300 may further include one or more elements.
  • the control unit 320 may be composed of one or more processor sets.
  • control unit 320 may include a set of a communication control processor, an application processor, an electronic control unit (ECU), a graphic processing processor, a memory control processor, and the like.
  • memory unit 330 may include RAM, dynamic RAM (DRAM), ROM, flash memory, volatile memory, non-volatile memory, and/or combinations thereof. can be configured.
  • AI devices include TVs, projectors, smartphones, PCs, laptops, digital broadcasting terminals, tablet PCs, wearable devices, set-top boxes (STBs), radios, washing machines, refrigerators, digital signage, robots, vehicles, etc. It may be implemented as a device or a movable device.
  • the AI device 600 includes a communication unit 610, a control unit 620, a memory unit 630, an input/output unit 640a/640b, a running processor unit 640c, and a sensor unit 640d.
  • a communication unit 610 can include a communication unit 610, a control unit 620, a memory unit 630, an input/output unit 640a/640b, a running processor unit 640c, and a sensor unit 640d.
  • Blocks 910 to 930/940a to 940d may respectively correspond to blocks 310 to 330/340 of FIG. 3 .
  • the communication unit 610 communicates wired and wireless signals (eg, sensor information, user data) with external devices such as other AI devices (eg, FIG. 1, 100x, 120, and 140) or AI servers (Fig. input, learning model, control signal, etc.) can be transmitted and received. To this end, the communication unit 610 may transmit information in the memory unit 630 to an external device or transmit a signal received from the external device to the memory unit 630 .
  • external devices eg, sensor information, user data
  • AI devices eg, FIG. 1, 100x, 120, and 140
  • AI servers Fig. input, learning model, control signal, etc.
  • the controller 620 may determine at least one executable operation of the AI device 600 based on information determined or generated using a data analysis algorithm or a machine learning algorithm. And, the controller 620 may perform the determined operation by controlling components of the AI device 600 . For example, the control unit 620 may request, retrieve, receive, or utilize data from the learning processor unit 640c or the memory unit 630, and may perform a predicted operation among at least one feasible operation or one determined to be desirable. Components of the AI device 600 may be controlled to execute an operation. In addition, the control unit 920 collects history information including user feedback on the operation contents or operation of the AI device 600 and stores it in the memory unit 630 or the running processor unit 640c, or the AI server ( 1, 140) can be transmitted to an external device. The collected history information can be used to update the learning model.
  • the memory unit 630 may store data supporting various functions of the AI device 600 .
  • the memory unit 630 may store data obtained from the input unit 640a, data obtained from the communication unit 610, output data of the learning processor unit 640c, and data obtained from the sensing unit 640.
  • the memory unit 930 may store control information and/or software codes required for operation/execution of the control unit 620 .
  • the input unit 640a may obtain various types of data from the outside of the AI device 600.
  • the input unit 620 may obtain learning data for model learning and input data to which the learning model is to be applied.
  • the input unit 640a may include a camera, a microphone, and/or a user input unit.
  • the output unit 640b may generate an output related to sight, hearing, or touch.
  • the output unit 640b may include a display unit, a speaker, and/or a haptic module.
  • the sensing unit 640 may obtain at least one of internal information of the AI device 600, surrounding environment information of the AI device 600, and user information by using various sensors.
  • the sensing unit 640 may include a proximity sensor, an illuminance sensor, an acceleration sensor, a magnetic sensor, a gyro sensor, an inertial sensor, an RGB sensor, an IR sensor, a fingerprint recognition sensor, an ultrasonic sensor, an optical sensor, a microphone, and/or a radar. there is.
  • the learning processor unit 640c may learn a model composed of an artificial neural network using learning data.
  • the running processor unit 640c may perform AI processing together with the running processor unit of the AI server (FIG. 1, 140).
  • the learning processor unit 640c may process information received from an external device through the communication unit 610 and/or information stored in the memory unit 630 .
  • the output value of the learning processor unit 940c may be transmitted to an external device through the communication unit 610 and/or stored in the memory unit 630.
  • 6G (radio communications) systems are characterized by (i) very high data rates per device, (ii) very large number of connected devices, (iii) global connectivity, (iv) very low latency, (v) battery- It aims to lower energy consumption of battery-free IoT devices, (vi) ultra-reliable connectivity, and (vii) connected intelligence with machine learning capabilities.
  • the vision of the 6G system can be four aspects such as “intelligent connectivity”, “deep connectivity”, “holographic connectivity”, and “ubiquitous connectivity”, and the 6G system can satisfy the requirements shown in Table 1 below. That is, Table 1 is a table showing the requirements of the 6G system.
  • the 6G system is enhanced mobile broadband (eMBB), ultra-reliable low latency communications (URLLC), mMTC (massive machine type communications), AI integrated communication, tactile Internet (tactile internet), high throughput, high network capacity, high energy efficiency, low backhaul and access network congestion and improved data security ( can have key factors such as enhanced data security.
  • eMBB enhanced mobile broadband
  • URLLC ultra-reliable low latency communications
  • mMTC massive machine type communications
  • AI integrated communication e.g., AI integrated communication
  • tactile Internet tactile internet
  • high throughput high network capacity
  • high energy efficiency high backhaul and access network congestion
  • improved data security can have key factors such as enhanced data security.
  • AI The most important and newly introduced technology for the 6G system is AI.
  • AI was not involved in the 4G system.
  • 5G systems will support partial or very limited AI.
  • the 6G system will be AI-enabled for full automation.
  • Advances in machine learning will create more intelligent networks for real-time communication in 6G.
  • Introducing AI in communications can simplify and enhance real-time data transmission.
  • AI can use a plethora of analytics to determine how complex target tasks are performed. In other words, AI can increase efficiency and reduce processing delays.
  • AI can also play an important role in M2M, machine-to-human and human-to-machine communications.
  • AI can be a rapid communication in the brain computer interface (BCI).
  • BCI brain computer interface
  • AI-based communication systems can be supported by metamaterials, intelligent structures, intelligent networks, intelligent devices, intelligent cognitive radios, self-sustaining wireless networks, and machine learning.
  • AI-based physical layer transmission means applying a signal processing and communication mechanism based on an AI driver rather than a traditional communication framework in fundamental signal processing and communication mechanisms. For example, deep learning-based channel coding and decoding, deep learning-based signal estimation and detection, deep learning-based multiple input multiple output (MIMO) mechanism, It may include AI-based resource scheduling and allocation.
  • MIMO multiple input multiple output
  • machine learning may be used for channel estimation and channel tracking, and may be used for power allocation, interference cancellation, and the like in a downlink (DL) physical layer.
  • Machine learning can also be used for antenna selection, power control, symbol detection, and the like in a MIMO system.
  • AI algorithms based on deep learning require a lot of training data to optimize training parameters.
  • a lot of training data is used offline. This is because static training on training data in a specific channel environment may cause a contradiction between dynamic characteristics and diversity of a radio channel.
  • Machine learning refers to a set of actions that train a machine to create a machine that can do tasks that humans can or cannot do.
  • Machine learning requires data and a running model.
  • data learning methods can be largely classified into three types: supervised learning, unsupervised learning, and reinforcement learning.
  • Neural network training is aimed at minimizing errors in the output.
  • Neural network learning repeatedly inputs training data to the neural network, calculates the output of the neural network for the training data and the error of the target, and backpropagates the error of the neural network from the output layer of the neural network to the input layer in a direction to reduce the error. ) to update the weight of each node in the neural network.
  • Supervised learning uses training data in which correct answers are labeled in the learning data, and unsupervised learning may not have correct answers labeled in the learning data. That is, for example, learning data in the case of supervised learning related to data classification may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network, and an error may be calculated by comparing the output (category) of the neural network and the label of the training data. The calculated error is back-propagated in a reverse direction (ie, from the output layer to the input layer) in the neural network, and the connection weight of each node of each layer of the neural network may be updated according to the back-propagation.
  • a reverse direction ie, from the output layer to the input layer
  • the amount of change in the connection weight of each updated node may be determined according to a learning rate.
  • the neural network's computation of input data and backpropagation of errors can constitute a learning cycle (epoch).
  • the learning rate may be applied differently according to the number of iterations of the learning cycle of the neural network. For example, a high learning rate is used in the early stages of neural network learning to increase efficiency by allowing the neural network to quickly achieve a certain level of performance, and a low learning rate can be used in the late stage to increase accuracy.
  • the learning method may vary depending on the characteristics of the data. For example, in a case where the purpose of the receiver is to accurately predict data transmitted by the transmitter in a communication system, it is preferable to perform learning using supervised learning rather than unsupervised learning or reinforcement learning.
  • the learning model corresponds to the human brain, and the most basic linear model can be considered. ) is called
  • the neural network cord used as a learning method is largely divided into deep neural networks (DNN), convolutional deep neural networks (CNN), and recurrent boltzmann machine (RNN). and this learning model can be applied.
  • DNN deep neural networks
  • CNN convolutional deep neural networks
  • RNN recurrent boltzmann machine
  • FIG. 5 is a diagram illustrating a functional framework. Communication may be performed based on AI/ML enabled RAN intelligence.
  • AI/ML algorithms may be configured in various forms.
  • an AI/ML-based operation may be performed according to an AI/ML functional configuration and corresponding inputs and outputs based on an AI/ML model pre-configured according to an AI/ML algorithm.
  • the data collection entity 510 may provide input data to a model training entity 540 and a model inference entity 520 .
  • the input data may include at least one of a measurement value by another network entity, a feedback value by terminals, and a feedback value for an output of the AI/ML model.
  • the training data provided by the data collection entity 510 to the model training entity 540 may be data provided for an AI/ML model training function.
  • inference data provided by the data collection entity 510 to the model inference entity 520 may be data provided for an AI/ML model inference function.
  • the model training entity 540 may be an entity that performs training, validation, and testing of AI/ML models.
  • the model training entity 540 may provide and update AI/ML models to the model inference entity 520 . Additionally, the model inference entity 520 may provide model performance feedback to the model training entity 540 . That is, the model training entity 540 performs training on the AI/ML model through the feedback of the model inference entity 520, and provides the updated AI/ML model back to the model inference entity 520. can do. In addition, the model inference entity 520 may receive inference data from the data collection entity 510 . Here, the model inference entity 520 may generate an output through the provided AI/ML model and provide it to the actor entity 530.
  • the actor entity 530 may be a subject that performs an operation according to an output, and the operation performed by the actor entity 530 may be fed back to the data collection entity 510 . Additionally, the fed back information may be provided back to the model training entity 540 as training data.
  • data for AI/ML model training is provided so that the AI/ML model is learned and built, and inference data is provided and output to the built AI/ML model so that AI/ML model-based operations can be performed.
  • FIG. 6 is a diagram illustrating a method of generating an AI/ML-based model inference output applicable to the present disclosure.
  • an NG-RAN node (NG-RAN node 1, 620) may have an AI/ML model.
  • the model inference of FIG. 5 may exist in NG-RAN node 1 620, and training may be performed in OAM 640. That is, training for the AI/ML model may not be performed at the RAN node, and the RAN node may have only model inference.
  • NG-RAN node 1 620 may receive data for AI/ML model inference based on network energy saving as required input data from another NG-RAN node 2 630.
  • NG-RAN node 2 630 may also have a model inference for an AI/ML model, and may not be essential.
  • the NG-RAN node 1 620 may obtain measurement information from the terminal 610.
  • NG-RAN node 1 620 may generate an output for model inference based on measurement data obtained from terminal 610 and data obtained from NG-RAN node 2 630 .
  • the output for the model inference may be an energy saving strategy or a handover strategy. That is, NG-RAN node 1 620 may perform handover or other operations for the terminal based on the model inference output, and is not limited to a specific embodiment.
  • at least one of NG-RAN node 1 620 and NG-RAN node 2 630 may transmit feedback to OAM 640, and training may be performed based on the feedback in OAM 640 there is.
  • NG-RAN node 1 720 may directly perform model training. Specifically, NG-RAN node 1 720 may receive data for AI/ML model inference based on network energy saving as required input data from another NG-RAN node 2 730. For example, NG-RAN node 2 730 may also have a model inference for an AI/ML model, and may not be essential. After that, the NG-RAN node 1 720 may obtain measurement information from the terminal 710.
  • NG-RAN node 1 720 may generate an output for model inference based on measurement data obtained from terminal 710 and data obtained from NG-RAN node 2 730 .
  • the output for the model inference may be an energy saving strategy or a handover strategy. That is, NG-RAN node 1 7620 may perform handover or other operations for the UE based on model inference out, and is not limited to a specific embodiment.
  • NG-RAN node 1 720 since NG-RAN node 1 720 has model training, it can directly perform training. To this end, NG-RAN node 1 720 may obtain feedback information from NG-RAN node 2 730, and through this, training may be performed directly.
  • the NG-RAN may require input data for AI/ML-based network energy saving.
  • the input data may include at least one of current or expected resource states of cells and adjacent nodes, current or predicted energy information of cells and adjacent nodes, and UE measurement reports (e.g. UE RSRP, RSRQ, SINR measurement, etc.) there is.
  • UE measurement reports e.g. UE RSRP, RSRQ, SINR measurement, etc.
  • the RAN may reuse the existing framework (including MDT and RRM measurement), and is not limited to a specific embodiment.
  • the output information for AI / ML-based network energy saving may include at least one of an energy saving strategy, a handover strategy including a recommended candidate cell for traffic handover, and expected energy information, but is limited to it may not be
  • the performance of the model may be optimized for AI/ML-based network energy saving.
  • the RAN node may acquire at least one of load measurement information and energy information as feedback information, but may not be limited thereto.
  • an AI/ML model may be considered for load balancing.
  • traffic distribution may not be easy due to the rapid increase in traffic used in commercial networks and multiple frequency bands, and an AI/ML model may be considered for load balancing.
  • Load balancing can be to evenly distribute the load between cells and between cell areas, or to transfer a portion of the traffic or offload the load in a congested cell or congested area of a cell.
  • load balancing may be performed through optimization of handover parameters and handover operation.
  • the traffic load and resource conditions of the network may cause degradation of service quality when a plurality of terminals with high mobility are connected. Therefore, it may be difficult to guarantee overall network and service performance when performing load balancing, and for this purpose, AI/ML models may be applied.
  • model training may be located in OAM and model inference may exist in a base station.
  • both model training and model inference may exist in the base station.
  • model training may exist in OAM and model inference may exist in gNB-CU.
  • model training and model inference may exist in the gNB-CU.
  • model training and model inference may exist in various locations and are not limited to a specific embodiment.
  • a gNB may request a load estimate from a neighboring node. If existing UE measurement is required at the gNB for AI/ML-based load balancing, the RAN may reuse the existing framework (including MDT and RRM measurement), but may not be limited thereto.
  • existing framework including MDT and RRM measurement
  • an AI/ML model may be considered for mobility optimization.
  • Mobility management may be a method of ensuring service continuity during mobility by minimizing call drop, radio link failure (RLF), unnecessary handover, and ping-pong.
  • RLF radio link failure
  • the handover frequency between nodes of a terminal may increase.
  • the handover frequency of terminals with high mobility may further increase.
  • QoE is sensitive to handover performance, so mobility management needs to avoid failed handovers and reduce latency during handover procedures.
  • AI/ML models can be considered.
  • the unintended event probability reduction, terminal location/mobility/performance prediction, and traffic steering may be performed using AI/ML.
  • the unintended event may be too late handover, too early handover, and handover operation to another cell of the UE in the intra system, but may not be limited thereto.
  • the location/mobility/performance prediction of the terminal may be performed by determining the best mobility target for maximizing efficiency and performance.
  • Traffic steering may mean adjusting a handover trigger point based on efficient resource processing and selecting an optimal cell combination to serve a user.
  • an AI/ML model may be required in consideration of the above-described operation.
  • model training based on the AI/ML model is deployed in OAM and model inference exists in RAN may be considered, which may be the same as in FIG. 6 described above.
  • both model training and model inference based on the AI/ML model may exist in the RAN, which may be as shown in FIG. 7 .
  • model training may be located in CU-CP or OAM, and model inference may be located in CU-CP, but may not be limited thereto.
  • FIG. 8 is a diagram illustrating a case in which both model training and model inference applicable to the present disclosure exist in the RAN.
  • NG-RAN node 1 820 may have both model training and model inference.
  • the NG-RAN node 1 820 provides measurement configuration information to the terminal 810, and based on this, the terminal 810 may perform measurement and deliver a measurement report to the NG-RAN node 1 820. . Then, NG-RAN node 1 820 may perform model training.
  • NG-RAN node 1 820 may derive an output by performing model inference based on the measurement report received from the terminal 810.
  • the output may be an operation for load balancing or mobility optimization as described above.
  • NG-RAN node 1 820 may request handover to NG-RAN node 2 830 or perform other operations, but is not limited to a specific embodiment. don't
  • an AI/ML-based operation can be performed in a new communication system (e.g. 6G).
  • AI/ML technology includes not only network technology, but also CSI feedback enhancement, beam management, positioning, RS overhead reduction, and RRM mobility enhancement (RRM). mobility enhancement), but may not be limited to a specific field.
  • RRM mobility enhancement
  • AI/ML can be applied to improve the technical fields of the PHY layer and the MAC/RRC layer between the terminal and the base station, and methods for this will be described below.
  • a scenario for improvement in an air interface such as RAN1/RAN2 through an AI/ML model may be shown in Table 2 below.
  • a scenario in which performance is improved by implementing an AI/ML model in at least one of a network and a terminal (case 1), an AI/ML model independently implemented in at least one of a network and a terminal and input/output (input/output) /output) to improve performance (case 2) and a scenario (case 3) to improve performance through sharing of AI/ML models implemented in networks or terminals.
  • case 3 a method of performing model training and model inference based on a scenario in which performance is improved through sharing of an AI/ML model implemented in a network or a terminal will be described. More specifically, model training may be performed in a network, and model inference may be a terminal or a scenario simultaneously performed in a terminal and a network, but may not be limited thereto.
  • FIG. 9 is a diagram illustrating a method in which AI/ML-based model training applicable to the present disclosure is performed in a network and model inference is performed in a terminal.
  • 10 is a diagram illustrating a method in which AI/ML-based model training applicable to the present disclosure is performed in a network and model inference is performed in a network and a terminal.
  • the network can collect various information from terminals.
  • the network may deploy a model that has been primarily trained, validated, and tested through offline learning based on information collected from terminals.
  • the network needs to share the built AI/ML model to terminals in the cell.
  • the network may share a shared model to terminals through synchronization, and based on this, may operate through the same model.
  • model update is required through model performance feedback or additional information (e.g., UE behavior such as RLF, BFR..)
  • the network refreshes the updated AI/ML model to the terminals after model update.
  • model update may also include online learning on the network side.
  • a terminal having AI/ML capabilities within a cell may perform communication based on the received AI/ML model, and through this, improved communication may be performed.
  • the base station 920 may share AI/ML model information built based on model training with the terminal 910.
  • the terminal 910 may derive an output through model inference of the shared AI/ML model and perform an action corresponding thereto, as described above. Thereafter, the terminal 910 provides feedback on model performance to the base station 920, and the base station 920 performs model training based on the feedback information and then shares the updated AI/ML model with the terminal 910.
  • the base station 1020 may share AI/ML model information built based on model training with the terminal 1010.
  • the terminal 1010 may derive output through model inference of the shared AI/ML model.
  • the base station 1020 may also derive output through model inference of the same AI/ML model.
  • the terminal 1010 and the base station 1020 may perform an action based on the output of the model inference, as described above.
  • the terminal 1010 provides feedback on model performance to the base station 1020, and the base station 1020 performs model training based on the feedback information and then shares the updated AI/ML model with the terminal 1010. can
  • the terminal needs to receive AI/ML model information.
  • the terminal needs to acquire cell-specific AI/ML model information from the network, and may need a method for acquiring this information.
  • the terminal may obtain AI/ML model information through a system information block (SIB) broadcast by the base station.
  • SIB system information block
  • AI / ML model information is broadcast through the SIB, there is a need to include all AI / ML model information in the broadcast message. Therefore, as the number of AI/ML model information to be transmitted increases, the reception load of the terminal may increase.
  • the base station may provide AI/ML model information to the terminal through a unicast message to the terminal requesting the AI/ML model information.
  • AI/ML models are shared using unicast messages
  • the number of unicast messages may increase as the number of terminals increases. Accordingly, signaling overhead and resource consumption may increase. Therefore, a method for the base station to efficiently share AI/ML model information with the terminal may be required.
  • the terminal needs to transmit the performance evaluation value (Model Performance Feedback, MPF) for the corresponding AI/ML model to the base station for model training, and below describes a method of transmitting the MPF and information included in the MPF do.
  • MPF Model Performance Feedback
  • the terminal can reduce unnecessary MPF transmission by transmitting the MPF according to a specific event rather than transmitting the MPF whenever a model inference occurs, which will be described later in this regard.
  • the terminal may receive setting information for a related MPF together with AI/ML model information trained in the network.
  • setting information for the MPF may be as shown in Table 3 below.
  • the setting information for the MPF may include parameters for the MPF of the AI/ML model or AI/ML model groups for each AI/ML model group.
  • parameters for MPF may be set identically for each AI/ML model or for each AI/ML model group.
  • one or more parameters may be set for each AI/ML model or AI/ML model group.
  • the setting information for the MPF may include trigger condition information for AI/ML model performance feedback.
  • trigger condition information for AI/ML model performance feedback may be set to a value that affects model update decision as a threshold for the feedback value, but is not limited to a specific embodiment.
  • trigger condition information for AI/ML model performance feedback may be information on a transmission method.
  • the MPF may be transmitted periodically.
  • the MPF may be configured to be transmitted whenever model inference is performed.
  • the MPF may be configured to be transmitted aperiodically based on a specific event.
  • setting information for MPF transmission may be set for each AI/ML model or each AI/ML model group.
  • the setting information for the MPF may be data information affecting the MPF.
  • the data information affecting the MPF is information on beams (CSI-RS/SSB quality) and CSI (eg CQI, PMI, RI) At least one of them may be included. That is, data information affecting the MPF may refer to parameters necessary for calculating the MPF, and all corresponding information may be included in function information for the MPF, and is not limited to a specific embodiment.
  • a terminal may receive at least one of AI/ML model information on which training is completed and model performance evaluation related information for the AI/ML model from a base station.
  • the terminal may receive AI/ML model information and sequentially receive model performance evaluation related information for the AI/ML model.
  • the terminal may receive model performance evaluation related information together with the AI/ML model, and is not limited to a specific embodiment.
  • the terminal may perform model inference in the corresponding AI/ML model based on the AI/ML model information received from the base station.
  • the terminal may perform model performance evaluation after performing the model inference.
  • the terminal may perform model performance evaluation using set model performance evaluation parameters whenever model inference is performed. That is, the terminal may generate a model performance evaluation feedback (MPF) value based on the model inference.
  • MPF model performance evaluation feedback
  • the terminal may determine whether to transmit the derived MPF to the base station.
  • MPF transmission may be at least one of periodic transmission, aperiodic transmission based on an event, and transmission upon generation of an MPF, but is not limited to a specific embodiment.
  • the UE may transmit the MPF to the BS.
  • whether to transmit the MPF may be determined based on information set by the base station.
  • the determination of whether to transmit the MPF may be determined based on an event determined by the terminal.
  • determination of whether to transmit the MPF may be determined based on a preset method, which may be shown in Table 4 below. However, it may not be limited thereto.
  • the terminal may transmit the MPF to the base station based on the above.
  • the factor for determining MPF transmission may be set to a value that affects the determination that the base station needs to update the performance of the model, but may not be limited thereto.
  • information included in the MPF may be as shown in Table 5 below, but is not limited thereto.
  • the MPF transmitted from the terminal to the base station may include indicator information indicating whether the model performance evaluation result value is worse than a preset value.
  • the threshold may be set to a preset value based on the network or terminal.
  • Indicator information indicating whether the model performance evaluation result value is better or worse than the threshold value may be included.
  • the indicator information may be set as 1-bit information for each AI/ML model (or AI/ML model group).
  • 1-bit information defines a resource or field for each AI/ML model, and may be indicated through bits of a fixed resource or field. For example, when the 1-bit indication information is a first value (or ON/true), the base station may recognize that the performance of the corresponding AI/ML model is lower than a specific reference point (or threshold value).
  • the network may update the AI/ML model by performing new AI/ML model training based on data related to the corresponding AI/ML model, and share the updated AI/ML model to terminals.
  • the MPF may include a model performance evaluation value. That is, the MPF may completely include model performance evaluation values.
  • the model performance evaluation value may be compared with a preset value (or threshold value) and transmitted only with a contrast difference value, thereby reducing transmission capacity. For example, based on the above, it may be expressed as information of a specific bit (e.g. n bit) size, and information of a fixed resource or field may be transmitted to the base station through resource or field definition for each AI / ML model.
  • the base station may receive a performance result value of the corresponding AI/ML model and recognize that the performance of the corresponding AI/ML model has deteriorated. That is, the network can obtain an accurate model performance result value, and based on this, it can determine whether new training for the AI/ML model is required.
  • the base station may update the AI/ML model by performing new AI/ML model training based on data related to the AI/ML model.
  • the base station can share the updated AI / ML model to the terminals.
  • the MPF may include values for data that affect model performance evaluation.
  • the value of the data that affects the model performance evaluation may be information about data that directly affects the performance among data that affects the evaluation result.
  • at least one of information about which parameter is a value of data that affects model performance evaluation and a value of the corresponding data may be included.
  • it may include only a quantized value or a differential value in consideration of a value for data, and may not be limited to a specific embodiment.
  • the values of data that affect model performance evaluation may not include information about a specific model.
  • values for data that affect model performance evaluation may include only information about the data.
  • values for data that affect model performance evaluation may be transmitted together with values for corresponding data, and are not limited to a specific embodiment.
  • information included in the MPF may be transmitted based on a scheme based on Table 6 below.
  • the terminal transmits physical (PHY) control information through at least one of a physical uplink control channel (PUCCH) and a physical uplink shared channel (PUSCH).
  • PUCCH physical uplink control channel
  • PUSCH physical uplink shared channel
  • specific resources corresponding to the corresponding AI/ML models may be allocated periodically.
  • at least one of the PUCCH resource and the PUSCH resource may be indicated through a UE-specific message for each UE or each AI/ML model.
  • the MPF indicates “poor performance” with 1 bit
  • information included in the MPF may be transmitted through a physical control channel, but may not be limited thereto.
  • the information included in the MPF is medium access control (MAC) control information and may be transmitted through an uplink shared channel (UL-SCH) through a new MAC control element (CE).
  • MAC medium access control
  • UL-SCH uplink shared channel
  • CE new MAC control element
  • MPF transmission for each AI/ML model may not require fast transmission. It may be advantageous to support information requiring rapid report to transmit information periodically or immediately when necessary by periodically allocating physical resources.
  • information included in the MPF may be transmitted to the base station through a resource request when the MPF is generated using MAC CE.
  • FIG. 12 may be a MAC CE format in which information included in an MPF applicable to the present disclosure is transmitted.
  • FIG. 12 (a) may be a format considering the case where up to 16 AI/ML models are set.
  • the MPF may be a 1-bit indicator indicating whether performance is poor compared to a preset value, and each field may correspond to 1-bit indication information.
  • the AI/ML model set to the first value may indicate that performance is evaluated below a specific reference value, but may not be limited thereto.
  • FIG. 12 (b) may indicate to the base station that AI/ML model performance is evaluated as poor by indicating a model index instead of transmission in a bitmap format.
  • the presence or absence of additional model index information following 1 byte information may be indicated using the E field.
  • FIG. 12(c) may be a format used when an MPF value for each AI/ML model is transmitted together.
  • a performance result value for the corresponding AI/ML model may be included and transmitted along with model index information.
  • the presence or absence of additional information based on a specific AI/ML model and performance result value may be indicated through the E field, and may not be limited to a specific embodiment.
  • information included in the MPF is RRC control information and may be transmitted through an uplink dedicated control channel (DCCH) based on a new RRC message or an information element (IE).
  • the new RRC message or the new IE may include at least one of a model index and an MPF value. For example, if the amount of information to be transmitted is large or if frequent transmission is not required, an RRC message that is not sensitive to delay may be required, but may not be limited thereto.
  • FIG. 13 is a diagram illustrating a terminal operation applicable to the present disclosure.
  • a terminal 1310 may receive MPF-related setting information while receiving an AI/ML model.
  • the terminal 1310 may receive MPF-related setting information after receiving the AI/ML model.
  • the MPF-related information may include at least one of resource information for transmitting the MPF by the terminal 1310, index information for AI/ML models, and event information for transmitting feedback.
  • the terminal 1310 may perform model inference and perform an action based on the model inference. That is, the terminal 1310 may cause an output value derived by the model inference to perform an operation for a specific procedure or function, and may perform an action based on the corresponding output.
  • the action may be an operation based on communication between the terminal 1310 and the network 1320, and may not be limited to a specific form.
  • the terminal 1310 may perform performance evaluation on the AI/ML model as a result of the action performed according to the model inference.
  • the terminal 1310 may determine whether the performance of the AI/ML model satisfies a reference value (or threshold value) based on event information set through AI/ML model related information. For example, when AI/ML model performance satisfies the reference value and is determined to be good, the terminal 1310 may not transmit MPF information to the network 1320.
  • a reference value or threshold value
  • the terminal 1310 may transmit the MPF to the network 1320 based on the AI/ML model MPF related information. .
  • prediction accuracy for each AI/ML model may be set as a parameter for MPF.
  • the prediction accuracy may be AI/ML model specific prediction accuracy.
  • the prediction accuracy is at least one of values for beam prediction, trajectory prediction, load prediction, CSI prediction, location prediction, and other predictions. It may include one, and may not be limited to a specific form.
  • CSI feedback e.g., CQI, CRI/SSBRI+RSRP, PMI
  • measurement values e.g., RSRP/RSRQ/SINR for a cell or SSB/CSI-RS
  • RSRP/RSRQ/SINR for a cell or SSB/CSI-RS
  • FIG. 14 is a diagram illustrating a terminal operation based on beam prediction applicable to the present disclosure.
  • the terminal 1410 may receive AI/ML model MPF related information from the network 1420 along with the AI/ML model or after receiving the AI/ML model, as described above.
  • information about beam quality prediction accuracy may be included in the MPF-related information for the AI/ML model.
  • the network 1420 may set the terminal 1410 to transmit the MPF only when the beam prediction accuracy based on the beam prediction model is 90% or less through an AI/ML model MPF related message, but is not limited thereto. can
  • the terminal 1410 may derive the predicted Reference Signal Received Power (RSRP) for the beams according to the received AI/ML model as an output.
  • the terminal 1410 may inform the network 1420 of information about the beam(s) having the highest RSRP based on the output information.
  • the network 1420 may perform beam change using the prediction value. That is, the terminal 1410 and the network 1420 may perform an action based on the model inference.
  • RSRP Reference Signal Received Power
  • the UE 1410 can evaluate the performance of the AI/ML model by comparing the actually measured RSRP for the actual beams with the previously predicted RSRP at the time the beam is changed. For example, when the prediction accuracy is 90% or more, the terminal 1410 may perform the next model inference using the corresponding AI/ML model without transmitting the MPF. That is, the preset value (or threshold value) may be 90%. On the other hand, if the model performance evaluation result accuracy is 90% or less, the terminal 1410 may transmit the MPF for the AI/ML model to the network 1420. Then, the network 1420 may update the AI/ML model based on the received MPF and provide the updated AI/ML model information to the terminal 1410.
  • 15 is a flowchart illustrating a terminal operation applicable to the present disclosure.
  • the terminal may receive at least one of AI/ML model information and MPF-related information of the AI/ML model.
  • the terminal may receive AI/ML model information.
  • MPF-related information of the ML model can be obtained.
  • the terminal may obtain MPF-related information of the AI/ML model together with AI/ML model information, as described above. After that, the terminal may perform model inference based on the AI/ML model.
  • the MPF-related information may include at least one of MPF parameter information of the AI/ML model, MPF triggering condition information, and MPF-related data information.
  • the MPF parameter may be identically set in at least one AI/ML model or may be set differently for each AI/ML model, as described above.
  • the MPF parameter information may include at least one of prediction accuracy information of the AI/ML model, CSI feedback information, and information about measurement values.
  • the terminal may obtain beam quality prediction accuracy information included in MPF parameter information.
  • the beam quality prediction accuracy information may include a preset beam quality prediction accuracy value for determining whether to transmit the MPF to the base station.
  • the terminal may perform RSRP prediction on at least one beam through model inference based on the AI/ML model and report the beam having the highest RSRP to the base station.
  • the base station can change the beam. That is, the terminal and the base station may perform an action based on the model inference.
  • the terminal may compare the actually measured RSRP for at least one or more beams with the RSRP prediction for at least one or more beams using the model performance evaluation result value. In this case, it may be determined whether to transmit the MPF to the base station based on whether the above-mentioned value is greater than or equal to the beam quality prediction accuracy value.
  • the aforementioned MPF triggering condition information may include at least one of threshold value information and transmission method information.
  • the threshold value information may include at least one of a threshold value for a feedback value and a threshold value related to update decision of the AI/ML model.
  • the transmission method information indicates the MPF transmission method of the AI / ML model, but the MPF may be transmitted based on at least one of periodic transmission, aperiodic transmission based on events, and transmission at the time of performing the model inference.
  • the terminal may perform an action based on an output of model inference of AI/ML model information, and may perform model performance evaluation based on the output and the action.
  • the terminal when the terminal decides not to transmit the MPF of the AI/ML model based on the model performance evaluation, the terminal may perform an action by generating an output based on the model inference of the AI/ML model.
  • the terminal when the terminal decides to transmit the MPF of the AI/ML model based on model performance evaluation, the terminal receives updated AI/ML model information from the base station and generates an output based on the updated AI/ML model. so you can perform the action. That is, the terminal may perform model inference through the updated AI/ML model.
  • whether to transmit the MPF of the AI/ML model may be determined based on at least one of an event set by a base station, an event set by a terminal, and a preset event.
  • the MPF may include at least one of 1-bit indication information indicating a performance state for each AI/ML model, a model performance evaluation result value of the AI/ML model, and a data value related to model performance evaluation.
  • the MPF includes 1-bit indication information indicating the performance state of each AI/ML model
  • the performance of each AI/ML model is based on the comparison between the model performance evaluation result value and the threshold value based on the model inference.
  • 1-bit indication information indicating a state may be determined and included in the MPF.
  • the MPF may include either a model performance evaluation result value or a value for the difference between the model performance evaluation result value and a preset value. there is.
  • the MPF when it is determined that the MPF of the AI/ML model is transmitted to the base station, the MPF may be indicated through at least one of PUCCH and PUSCH. As another example, when it is determined that the MPF of the AI/ML model is transmitted to the base station, the MPF may be included in the MAC CE and transmitted. As another example, when it is determined that the MPF of the AI/ML model is transmitted to the base station, the MPF may be transmitted through an uplink designated control channel based on the RRC message.
  • 16 is a flowchart illustrating a terminal operation applicable to the present disclosure.
  • the base station may transmit at least one of AI/ML model information and MPF-related information of the AI/ML model (S1610).
  • the base station transmits AI/ML model information and then transmits AI/ML model information MPF related information of may be additionally transmitted.
  • the base station may transmit MPF-related information of the AI/ML model together with AI/ML model information, as described above. After that, the base station may perform an action based on the model inference performance result of the terminal. (1620) After that, the terminal derives a model performance evaluation result value based on the model inference, and based on this, You can decide whether or not to transmit the MPF.
  • the base station may receive the MPF from the terminal (S1630).
  • the MPF-related information includes MPF parameter information of the AI/ML model and MPF triggering It may include at least one of condition information and MPF related data information.
  • the MPF parameter may be identically set in at least one AI/ML model or may be set differently for each AI/ML model, as described above.
  • the MPF parameter information may include at least one of prediction accuracy information of the AI/ML model, CSI feedback information, and information about measurement values.
  • the terminal may obtain beam quality prediction accuracy information included in MPF parameter information from the base station.
  • the beam quality prediction accuracy information may include a preset beam quality prediction accuracy value for determining whether to transmit the MPF to the base station.
  • the terminal may perform RSRP prediction on at least one beam through model inference based on the AI/ML model and report the beam having the highest RSRP to the base station.
  • the base station can change the beam. That is, the terminal and the base station may perform an action based on the model inference.
  • the terminal may compare the actually measured RSRP for at least one or more beams with the RSRP prediction for at least one or more beams using the model performance evaluation result value. In this case, it may be determined whether to transmit the MPF to the base station based on whether the above-mentioned value is greater than or equal to the beam quality prediction accuracy value.
  • the aforementioned MPF triggering condition information may include at least one of threshold value information and transmission method information.
  • the threshold value information may include at least one of a threshold value for a feedback value and a threshold value related to update decision of the AI/ML model.
  • the transmission method information indicates the MPF transmission method of the AI / ML model, but the MPF may be transmitted based on at least one of periodic transmission, aperiodic transmission based on events, and transmission at the time of performing the model inference.
  • the terminal may perform an action based on an output of model inference of AI/ML model information, and may perform model performance evaluation based on the output and the action.
  • the terminal when the terminal decides not to transmit the MPF of the AI/ML model based on the model performance evaluation, the terminal may perform an action by generating an output based on the model inference of the AI/ML model.
  • the terminal when the terminal decides to transmit the MPF of the AI/ML model based on model performance evaluation, the terminal receives updated AI/ML model information from the base station and generates an output based on the updated AI/ML model. so you can perform the action. That is, the terminal may perform model inference through the updated AI/ML model.
  • whether to transmit the MPF of the AI/ML model may be determined based on at least one of an event set by a base station, an event set by a terminal, and a preset event.
  • the MPF may include at least one of 1-bit indication information indicating a performance state for each AI/ML model, a model performance evaluation result value of the AI/ML model, and a data value related to model performance evaluation.
  • the MPF includes 1-bit indication information indicating the performance state of each AI/ML model
  • the performance of each AI/ML model is based on the comparison between the model performance evaluation result value and the threshold value based on the model inference.
  • 1-bit indication information indicating a state may be determined and included in the MPF.
  • the MPF may include either a model performance evaluation result value or a value for the difference between the model performance evaluation result value and a preset value. there is.
  • the MPF when it is determined that the MPF of the AI/ML model is transmitted to the base station, the MPF may be indicated through at least one of PUCCH and PUSCH. As another example, when it is determined that the MPF of the AI/ML model is transmitted to the base station, the MPF may be included in the MAC CE and transmitted. As another example, when it is determined that the MPF of the AI/ML model is transmitted to the base station, the MPF may be transmitted through an uplink designated control channel based on the RRC message.
  • Embodiments of the present disclosure may be applied to various wireless access systems.
  • various wireless access systems there is a 3rd Generation Partnership Project (3GPP) or 3GPP2 system.
  • 3GPP 3rd Generation Partnership Project
  • 3GPP2 3rd Generation Partnership Project2
  • Embodiments of the present disclosure may be applied not only to the various wireless access systems, but also to all technical fields to which the various wireless access systems are applied. Furthermore, the proposed method can be applied to mmWave and THz communication systems using ultra-high frequency bands.
  • embodiments of the present disclosure may be applied to various applications such as free-running vehicles and drones.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Electromagnetism (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

La présente divulgation concerne un procédé de fonctionnement d'un terminal dans un système de communication sans fil. Le procédé peut comprendre les étapes consistant à : au moyen d'un terminal, recevoir un signal de synchronisation provenant d'une station de base ; sur la base du signal de synchronisation, transmettre un préambule d'accès aléatoire à la station de base ; sur la base du préambule d'accès aléatoire, recevoir une réponse d'accès aléatoire ; après la réception de la réponse d'accès aléatoire, établir une connexion à la station de base ; recevoir des informations sur un modèle AI/ML et/ou des informations relatives à un retour de performances de modèle associé au modèle AI/ML et provenant de la station de base ; puis, sur la base des informations sur le modèle AI/ML, effectuer une inférence de modèle dans le modèle AI/ML et déterminer s'il faut transmettre le MPF du modèle AI/ML à la station de base par l'intermédiaire d'une évaluation des performances du modèle.
PCT/KR2022/018624 2021-11-30 2022-11-23 Procédé et appareil de réalisation d'une communication dans un système de communication sans fil WO2023101304A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020247010151A KR20240116893A (ko) 2021-11-30 2022-11-23 무선 통신 시스템에서 통신을 수행하는 방법 및 장치

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR20210169081 2021-11-30
KR10-2021-0169081 2021-11-30

Publications (1)

Publication Number Publication Date
WO2023101304A1 true WO2023101304A1 (fr) 2023-06-08

Family

ID=86612715

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2022/018624 WO2023101304A1 (fr) 2021-11-30 2022-11-23 Procédé et appareil de réalisation d'une communication dans un système de communication sans fil

Country Status (2)

Country Link
KR (1) KR20240116893A (fr)
WO (1) WO2023101304A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024180067A1 (fr) * 2023-02-27 2024-09-06 Sony Group Corporation Commutation vers un autre modèle d'apprentissage automatique

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101482498B1 (ko) * 2008-01-11 2015-01-13 엘지전자 주식회사 무선통신 시스템에서 랜덤 액세스 과정 수행 방법
US20210274361A1 (en) * 2019-05-31 2021-09-02 At&T Intellectual Property I, L.P. Machine learning deployment in radio access networks

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101482498B1 (ko) * 2008-01-11 2015-01-13 엘지전자 주식회사 무선통신 시스템에서 랜덤 액세스 과정 수행 방법
US20210274361A1 (en) * 2019-05-31 2021-09-02 At&T Intellectual Property I, L.P. Machine learning deployment in radio access networks

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
DEUTSCHE TELEKOM (MODERATOR): "CB: # AIRAN1_Framework - Summary of email discussion", 3GPP TSG-RAN3 MEETING #114-E, R3-215908, 9 November 2021 (2021-11-09), XP052082731 *
LENOVO, MOTOROLA MOBILITY: "Summary of offline discussion on AI RAN general framework", 3GPP TSG-RAN WG3 #113E, R3-214220, 24 August 2021 (2021-08-24), XP052043385 *
NEC: "Proposed TP to TR 37.817 on high-level principles and functional framework", 3GPP TSG-RAN WG3 #113-E, R3-213294, 6 August 2021 (2021-08-06), XP052035218 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024180067A1 (fr) * 2023-02-27 2024-09-06 Sony Group Corporation Commutation vers un autre modèle d'apprentissage automatique

Also Published As

Publication number Publication date
KR20240116893A (ko) 2024-07-30

Similar Documents

Publication Publication Date Title
WO2022186657A1 (fr) Procédé et appareil de prise en charge de techniques d'apprentissage machine (ml) ou d'intelligence artificielle (ai) dans des systèmes de communication
WO2019245329A1 (fr) Appareil et procédé de réalisation d'un changement de cellule conditionnel dans un système de communication sans fil
WO2022186659A1 (fr) Procédé et appareil d'estimation de canal et de d'améliorations de mobilité dans un système de communication sans fil
WO2019245304A1 (fr) Procédé et appareil de réalisation de changement de cellule conditionnel sur la base d'une occupation de canal dans un système de communication sans fil
WO2021066451A1 (fr) Procédé de fonctionnement lié à un sci de second étage d'un ue dans un système de communication sans fil
WO2023277454A1 (fr) Procédé et appareil de classification d'environnement de canal dans un système de réseau sans fil
WO2022191493A1 (fr) Procédé et appareil de prise en charge de techniques d'apprentissage automatique ou d'intelligence artificielle pour la gestion de transferts dans des systèmes de communication
WO2022080702A1 (fr) Procédé de fonctionnement d'équipement utilisateur associé à un relais de liaison latérale et à une défaillance de liaison radio dans un système de communication sans fil
WO2020105833A1 (fr) Procédé d'attribution de ressources pour un nœud relais dans un système de communication de prochaine génération, et dispositif associé
WO2020197125A1 (fr) Procédé et appareil d'exécution de mesurage dans un système de communications sans fil
WO2023101304A1 (fr) Procédé et appareil de réalisation d'une communication dans un système de communication sans fil
US20240073732A1 (en) Method and device for adjusting split point in wireless communication system
WO2022065665A1 (fr) Procédé et appareil de gestion de faisceau dans un système de communication sans fil
WO2023017881A1 (fr) Appareil et procédé pour effectuer un transfert sur la base d'un résultat de mesure à l'aide d'un intervalle de mesure dans un système de communication sans fil
WO2022139230A1 (fr) Procédé et dispositif pour ajuster un point de division dans un système de communication sans fil
WO2023101303A1 (fr) Procédé et dispositif d'exécution d'une communication dans un système de communication sans fil
WO2020071880A1 (fr) Amélioration d'une procédure de radiomessagerie
WO2023017882A1 (fr) Appareil et procédé pour sélectionner une technologie d'accès radio en tenant compte de l'efficacité de batterie dans un système de communication sans fil
WO2023013857A1 (fr) Procédé et dispositif pour exécuter un apprentissage de données dans un système de communication sans fil
WO2024010103A1 (fr) Procédé et dispositif de mise en œuvre de demande de ressource dans un système de communication sans fil
WO2024048803A1 (fr) Dispositif et procédé de configuration de paramètres associés à une opération de réception discontinue dans un système de communication sans fil
WO2023058872A1 (fr) Dispositif et procédé d'exécution d'un transfert intercellulaire sur la base d'une position dans un système de communication sans fil
WO2023277218A1 (fr) Procédé et dispositif de transmission de signal à travers une plaque réfléchissante dans un système de communication sans fil
WO2023042938A1 (fr) Procédé et dispositif de transmission d'un signal à travers une plaque de réflexion dans un système de communication sans fil
WO2024058372A1 (fr) Procédé et dispositif d'économie d'énergie à l'aide d'une intelligence artificielle basée sur des informations de contexte dans un système de communication sans fil

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22901662

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE